People

Picture This: High-Tech Wheelchair Moves by Reading Your Mind

September 1, 2016Posted by Terry Turner

Full smile, half-smile, duck face, tongue out, and puffy cheeks aren’t selfie poses: they’re the commands steering a computerized wheelchair.

The Wheelie recognizes dozens of facial expressions, each of which can be programmed to match a particular movement, speed, or direction for the wheelchair. It’s the brainchild of Brazilian researchers looking to meet the needs of people living with cerebral palsy, amyotrophic lateral sclerosis (Lou Gehrig’s Disease), and other conditions that prevent them from using a chair’s standard joystick.

Researchers were working on brain-computer interface (BCI) technology—which directly converts brain waves into commands a computer can read—when they decided to try the same facial recognition technology used by law enforcement and anti-terrorism forces.

It’s almost as though, by combining a 3D camera with Intel’s RealSense technology, the chair’s computer is able to read the user’s mind.

“The camera identifies more than 70 points on the face around the mouth, nose and eyes, and simple commands can be extracted from movements at these points, such as forward, back, left or right, and, most importantly, stop,” said Eleri Cardozo, a professor at the University of Campinas School of Electrical & Computer Engineering in São Paulo.

project

The Wheelie is the brainchild of Paulo Gurgel Pinheiro, Professor Cardozo’s post-doctoral adviser when the concept for the wheelchair first came up. He was so convinced the Wheelie could make a positive difference in people’s lives, he gave up his teaching post to start Hoo-Box, a company dedicated to building the medical mobility devices.

“Since Wheelie can support many different face expressions, we hope it can be a great fit for people with ALS in different stages of the disease,” Pinheiro said.

In fact, Hoo-Box has rushed some models into use for people with ALS (also called Lou Gehrig’s Disease), even as tests continue on a final production model.

In one test, the researchers put the chair through a 20 yard course, reading 40 different expressions in just under three minutes. Along the way, the chair had to turn, rotate, and make other maneuvers. Its forward speed averaged just under a half mile per hour, and rotating speeds were just about half that.

Dustin Jones, President and Founder of United For Equal Access New York and Co-Creator of Wheely NYC, is familiar with present day technology that allows people to move their wheelchairs using movement of the head and air blown into a tube, which to this day remains a remarkable innovation. This newest development, he says, sounds promising. 

“Not long ago, if you had severe cerebral palsy or other disabilities that did not allow you to move your limbs the way everybody else does you would have to be pushed and controlled by someone else,” said Jones. “These types of chairs allow people with disabilities to be independent.”

Screen Shot 2016-05-19 at 10.13.55 PM

Pinheiro believes “Wheelie can take advantage of the best ability of a person to counterpoint to his/her deficiency, not only to improve the mobility and autonomy, but also to enhance the self-esteem of the users.”

The Wheelie team is also focusing on full BCI control for future models. Engineers at The University of South Florida have used that technology to control a robot arm that can be mounted on wheelchairs. Rajiv Dubey, professor and chair of the USF Department of Mechanical Engineering had said that he believes  the technology can lead to “improved quality of life and even better employment outcomes.”

The real trick, though, is making the Wheelie affordable, which, by the researchers’ standards, is about $2,000, about twice as much as today’s average motorized wheelchair.

Pinheiro and Hoo-Box hope to have the chairs rolling off the assembly line within two years.

Related Post

Share this article:
Facebooktwitterlinkedinmail

#

Browse other categories:

Make a Comment or Leave a Reply

Your email address will not be published. Required fields are marked *